Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.33845v1 Announce Type: new Abstract: Can LLM agents carry a hard real-world problem from raw data to a system that holds its own against people? We study this in Hearthstone Battlegrounds,...
arXiv:2610.33949v1 Announce Type: cross Abstract: Pipelines that require structured outputs from hosted language models often specify a Pydantic schema in the prompt, validate the response, and retry...
arXiv:2610.33957v1 Announce Type: cross Abstract: We propose a joint sparse sample weighting and parameter estimation (SWAPE) framework that jointly optimizes model parameters and sample weights to t...
The paper introduces T2D, a framework that prunes and adapts a target large language model into a draft model optimized for both inference latency and alignment with the target model’s outputs. By formulating draft model design as an optimization problem, T2D achieves up to 92% pruning while maintaining high speculative decoding performance across multiple target model families and domains. The resulting draft models can also be integrated with other speculative decoding techniques to yield additional gains.
arXiv:2610.34623v1 Announce Type: new Abstract: Text injection trains speech recognition models on unpaired text alongside paired audio. We feed the speech encoder synthetic input derived from text s...
arXiv:2610.34703v1 Announce Type: new Abstract: Simulation-based inference often encodes observations $Y$ into a fixed-dimensional summary $S$, with the posterior conditioning only on $S$. While exac...
arXiv:2610.35077v1 Announce Type: cross Abstract: Understanding and operating with scientific charts is a standard approach in data analysis, and while humans are good at interpreting such charts, op...
arXiv:2402.03941v4 Announce Type: replace-cross Abstract: Revealing hidden causal variables alongside the underlying causal mechanisms is essential to the development of science. Despite the progress...
arXiv:2509.06984v4 Announce Type: replace-cross Abstract: Federated Learning with LoRA fine-tuning offers an efficient and privacy-aware solution for institutions to collaboratively leverage their la...
arXiv:2510.15038v2 Announce Type: replace-cross Abstract: Flow-based Generative Models (FGMs) effectively transform noise into complex data distributions. Incorporating Optimal Transport (OT) to coup...
arXiv:2511.03190v2 Announce Type: replace-cross Abstract: Attention mechanisms are effective for multivariate time series modeling because they adaptively aggregate information across timestamps and...
arXiv:2605.10981v2 Announce Type: replace-cross Abstract: Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Pre...
arXiv:2605.12049v2 Announce Type: replace-cross Abstract: Cortical neurons are complex, multi-timescale processors wired into recurrent circuits, shaped by long evolutionary pressure under stringent...
arXiv:2605.21856v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines...
arXiv:2511.22451v3 Announce Type: replace Abstract: Machine-learning models for quantum-dot state recognition are commonly trained using synthetic data, where large labeled datasets can be generated...
arXiv:2604.08362v3 Announce Type: replace-cross Abstract: The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmark...
arXiv:2605.06285v2 Announce Type: replace Abstract: Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks...
arXiv:2605.12718v2 Announce Type: replace Abstract: Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain st...
arXiv:2605.24155v2 Announce Type: replace-cross Abstract: Effective skills-aware talent recommendation must balance behavioral transition patterns, trajectory-sensitive adaptation, and inspectable oc...
arXiv:2608.25302v2 Announce Type: replace Abstract: Guided depth super-resolution (GDSR) typically extracts RGB guidance features through convolutional hierarchies, inheriting their fine-to-coarse bi...